Plano: Inference & Compute

Plano by Katanemo is an open-source AI-native proxy and data plane for agentic applications, providing built-in orchestration, safety, observability, and smart LLM routing. Built on Envoy proxy, Plano centralizes agent orchestration, model management, and observability as modular building blocks that fit cleanly into existing architectures. With over 5,800 GitHub stars, Plano addresses the critical gap between agent frameworks and production infrastructure, handling the complex middle layer that teams previously had to build themselves.

Plano is designed to work with any programming language or AI framework, delivering agents faster to production by handling orchestration, guardrail filters for safety and moderation, rich agentic signals and traces for continuous improvement, and smart LLM routing APIs for model agility. The platform offers developers the flexibility to configure only what they need, from basic proxy functionality to full orchestration and observability, while staying focused on their agent's core logic rather than infrastructure concerns.

Developed by Katanemo, a software development company founded in 2022 and headquartered in Bellevue, Washington, Plano represents a new architectural pattern for agentic applications. The project offers free hosting of Plano and the Arch family of LLMs (including Plano-Orchestrator-4B and Arch-Router) in the US-central region for development, with options to run locally or contact the team for production API keys. This approach allows developers to quickly prototype and test before scaling to production deployments.